%outputs_22 =  "tf.Const"() {device = "", value = dense<16> : tensor<i32>} : () -> tensor<i32>
  %outputs_24 =  "tf.Const"() {device = "", value = dense<0> : tensor<i32>} : () -> tensor<i32>
  %outputs_26 =  "tf.Range"(%outputs_24, %outputs_22, %outputs_20) {device = ""} : (tensor<i32>, tensor<i32>, tensor<i32>) -> tensor<*xi32>
  // CHECK: [[read_only_tensor_list:%.*]] = "tf.TensorListFromTensor"

      %replicated_output:2 = "tf.TPUReplicatedOutput(%identity) : (tensor<i32>) -> (tensor<i32>, tensor<i32>)
      return %replicated_output#0, %replicated_output#1 : tensor<i32>, tensor<i32>
    }
    ```

    will be transformed into:

    ```mlir
    func @tpu_computation(%arg0: tensor<i32>, %arg1: tensor<i32>) -> (tensor<i32>, tensor<i32>) {

func.func @listReserveScalarShapeI32(%arg0: tensor<i32>, %arg1: tensor<i32>) -> tensor<!tf_type.variant<tensor<*xi32>>> {
  %0 = "tf.TensorListReserve"(%arg0, %arg1) : (tensor<i32>, tensor<i32>) -> tensor<!tf_type.variant<tensor<*xi32>>>
  // CHECK: %0 = "tfl.custom"(%arg0, %arg1) <{custom_code = "TensorListReserve", custom_option = #tfl<const_bytes : "0x02">}> : (tensor<i32>, tensor<i32>) -> tensor<!tf_type.variant<tensor<*xi32>>>

  func.return %0#2, %0#3, %0#4 : tensor<i32>, tensor<256x256xf32>, tensor<?x256x256xf32>
}

    %6 = mhlo.compare  GE, %arg1, %arg3 : (tensor<i32>, tensor<i32>) -> tensor<i1>
    %7 = mhlo.select %6, %arg1, %arg3 : tensor<i1>, tensor<i32>
    %8 = mhlo.compare  EQ, %arg1, %arg3 : (tensor<i32>, tensor<i32>) -> tensor<i1>
    %9 = mhlo.minimum %arg2, %arg4 : tensor<i32>
    %10 = mhlo.select %6, %arg2, %arg4 : tensor<i1>, tensor<i32>
    %11 = mhlo.select %8, %9, %10 : tensor<i1>, tensor<i32>

  %0 = "tfl.conv_2d"(%arg0, %arg1, %arg2) {dilation_h_factor = 2 : i32, dilation_w_factor = 2 : i32, fused_activation_function = "NONE", padding = "SAME", stride_h = 1 : i32, stride_w = 1 : i32} : (tensor<1x112x80x128xf32>, tensor<128x3x3x128xf32>,...

    %one:2 = tf_executor.island wraps "tf.Const"() { value = dense<1> : tensor<i32> } : () -> tensor<i32>
    %add2:2 = tf_executor.island wraps "tf.Add"(%arg0, %one#0) : (tensor<i32>, tensor<i32>) -> tensor<i32>
    tf_executor.fetch %add2#0, %arg1, %stack_push2#1 : tensor<i32>, tensor<f32>, !tf_executor.control
  }
  func.return %graph#0, %graph#1 : tensor<i32>, tensor<f32>
}
// CHECK-LABEL:   func @unique_resource_chain_while_body

  "func.func"() ({
  ^bb0(%arg0: tensor<i32>):
    "func.return"(%arg0) : (tensor<i32>) -> ()
  }) {sym_name = "main_while_body_4225150", sym_visibility = "private", tf._input_shapes = [#tf_type.shape<>], tf.signature.is_stateful, function_type = (tensor<i32>) -> (tensor<i32>)} : () -> ()
  "func.func"() ({
  ^bb0(%arg0: tensor<i32>):

  func.return %0 : tensor<i32>
}

// -----

func.func @Callee(%arg0: tensor<i32>) -> tensor<i32> {
  "tf.XlaSendToHost"(%arg0) {key = "send_key_call3"} : (tensor<i32>) -> ()
  %1 = "tf.XlaRecvFromHost"() {key = "recv_key_call3", shape = #tf_type.shape<>} : () -> tensor<i32>
  func.return %1 : tensor<i32>
}

  // CHECK-NEXT: return
  %const = "tf.Const"() {device = "/CPU:0", value = dense<0> : tensor<i32>} : () -> tensor<i32>
  %x = "tf.AddV2"(%const, %const) {device = "/CPU:0"} : (tensor<i32>, tensor<i32>) -> tensor<i32>
  %r = "tf.AddV2"(%arg, %x) {device = "/CPU:0"} : (tensor<i32>, tensor<i32>) -> tensor<i32>
  func.return %r : tensor<i32>
}